7 papers
SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale
Tong Bai, Zhenglin Wan, Pengfei Zhou +3
As LLM agents adopt large skill libraries, selecting the right subset becomes a structural problem rather than a similarity-matching one: skills depend on, conflict with, specializ…
Training Diffusion Policies via Prior-Mapping Co-Evolution
Chubin Zhang, Zhenglin Wan, Feng Chen +7
Reinforcement learning (RL) faces a persistent tension: policies that are stable to optimize (e.g., Gaussians) are often too simple to represent the multimodal action distributions…
Adversarial Dual On-Policy Distillation from Expressive Teacher
Zhenglin Wan, Jingxuan Wu, Xingrui Yu +5
Learning from demonstrations in embodied control is often cast as behavioral cloning, and recent diffusion or flow-matching policies improve this paradigm by modeling multi-modal e…
PhysMem: Scaling Test-Time Memory for Embodied Physical Reasoning
Haoyang Li, Yang You, Hao Su +1
Reliable object manipulation requires understanding physical properties that vary across objects and environments. Vision-language model (VLM) planners can reason about friction an…
SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling
Yiqi Zhang, Huiqiang Jiang, Xufang Luo +7
Scaling reinforcement learning (RL) has shown strong promise for enhancing the reasoning abilities of large language models (LLMs), particularly in tasks requiring long chain-of-th…
ViReSkill: Vision-Grounded Replanning with Skill Memory for LLM-Based Planning in Lifelong Robot Learning
Tomoyuki Kagaya, Subramanian Lakshmi, Anbang Ye +6
Robots trained via Reinforcement Learning (RL) or Imitation Learning (IL) often adapt slowly to new tasks, whereas recent Large Language Models (LLMs) and Vision-Language Models (V…